{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 639,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047058823529411764,
      "grad_norm": 5.211361885070801,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 1.7904388427734375,
      "step": 10
    },
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 3.353734254837036,
      "learning_rate": 5.9375e-05,
      "loss": 1.0248506546020508,
      "step": 20
    },
    {
      "epoch": 0.1411764705882353,
      "grad_norm": 2.6654064655303955,
      "learning_rate": 9.062500000000001e-05,
      "loss": 0.7279780864715576,
      "step": 30
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 2.952399730682373,
      "learning_rate": 9.996718964356489e-05,
      "loss": 0.5767448902130127,
      "step": 40
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 3.0830438137054443,
      "learning_rate": 9.980658950985476e-05,
      "loss": 0.5082252979278564,
      "step": 50
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 2.35514760017395,
      "learning_rate": 9.951260277060386e-05,
      "loss": 0.3946207046508789,
      "step": 60
    },
    {
      "epoch": 0.32941176470588235,
      "grad_norm": 1.618377685546875,
      "learning_rate": 9.908601674920869e-05,
      "loss": 0.3993117094039917,
      "step": 70
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 1.798601508140564,
      "learning_rate": 9.85279738820803e-05,
      "loss": 0.399346923828125,
      "step": 80
    },
    {
      "epoch": 0.4235294117647059,
      "grad_norm": 1.5165961980819702,
      "learning_rate": 9.783996865909492e-05,
      "loss": 0.3666198968887329,
      "step": 90
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 3.2555081844329834,
      "learning_rate": 9.702384362121333e-05,
      "loss": 0.3828256607055664,
      "step": 100
    },
    {
      "epoch": 0.5176470588235295,
      "grad_norm": 2.4359097480773926,
      "learning_rate": 9.60817844259875e-05,
      "loss": 0.40076642036437987,
      "step": 110
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 2.1507678031921387,
      "learning_rate": 9.50163139941696e-05,
      "loss": 0.30626022815704346,
      "step": 120
    },
    {
      "epoch": 0.611764705882353,
      "grad_norm": 1.606743335723877,
      "learning_rate": 9.383028575309933e-05,
      "loss": 0.345287561416626,
      "step": 130
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 2.060086965560913,
      "learning_rate": 9.252687599496429e-05,
      "loss": 0.316464900970459,
      "step": 140
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.7956825494766235,
      "learning_rate": 9.110957537039881e-05,
      "loss": 0.3166621685028076,
      "step": 150
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 2.184234857559204,
      "learning_rate": 8.958217954020207e-05,
      "loss": 0.3145156383514404,
      "step": 160
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.64579176902771,
      "learning_rate": 8.794877901021093e-05,
      "loss": 0.3417710065841675,
      "step": 170
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 1.6739730834960938,
      "learning_rate": 8.62137481765511e-05,
      "loss": 0.32343525886535646,
      "step": 180
    },
    {
      "epoch": 0.8941176470588236,
      "grad_norm": 0.965537428855896,
      "learning_rate": 8.438173361060373e-05,
      "loss": 0.31631155014038087,
      "step": 190
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.8127070665359497,
      "learning_rate": 8.245764161506205e-05,
      "loss": 0.3077380657196045,
      "step": 200
    },
    {
      "epoch": 0.9882352941176471,
      "grad_norm": 1.892673373222351,
      "learning_rate": 8.044662508440368e-05,
      "loss": 0.2876445770263672,
      "step": 210
    },
    {
      "epoch": 1.0329411764705883,
      "grad_norm": 1.4413647651672363,
      "learning_rate": 7.835406970496751e-05,
      "loss": 0.2558260917663574,
      "step": 220
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.1115148067474365,
      "learning_rate": 7.618557953159282e-05,
      "loss": 0.21869213581085206,
      "step": 230
    },
    {
      "epoch": 1.1270588235294117,
      "grad_norm": 5.942924976348877,
      "learning_rate": 7.394696197944734e-05,
      "loss": 0.25175426006317136,
      "step": 240
    },
    {
      "epoch": 1.1741176470588235,
      "grad_norm": 1.9588311910629272,
      "learning_rate": 7.164421227123806e-05,
      "loss": 0.23550641536712646,
      "step": 250
    },
    {
      "epoch": 1.2211764705882353,
      "grad_norm": 1.588170051574707,
      "learning_rate": 6.928349738145588e-05,
      "loss": 0.1901813864707947,
      "step": 260
    },
    {
      "epoch": 1.2682352941176471,
      "grad_norm": 1.4131890535354614,
      "learning_rate": 6.687113952065362e-05,
      "loss": 0.20258448123931885,
      "step": 270
    },
    {
      "epoch": 1.315294117647059,
      "grad_norm": 1.3011943101882935,
      "learning_rate": 6.441359920398737e-05,
      "loss": 0.2526524305343628,
      "step": 280
    },
    {
      "epoch": 1.3623529411764705,
      "grad_norm": 1.7695306539535522,
      "learning_rate": 6.191745794936561e-05,
      "loss": 0.18704546689987184,
      "step": 290
    },
    {
      "epoch": 1.4094117647058824,
      "grad_norm": 1.3404783010482788,
      "learning_rate": 5.938940065154185e-05,
      "loss": 0.21009507179260253,
      "step": 300
    },
    {
      "epoch": 1.4564705882352942,
      "grad_norm": 0.9719374775886536,
      "learning_rate": 5.6836197679354564e-05,
      "loss": 0.1803208112716675,
      "step": 310
    },
    {
      "epoch": 1.5035294117647058,
      "grad_norm": 0.7226787805557251,
      "learning_rate": 5.426468674405985e-05,
      "loss": 0.21167051792144775,
      "step": 320
    },
    {
      "epoch": 1.5505882352941176,
      "grad_norm": 0.9939029812812805,
      "learning_rate": 5.1681754587314625e-05,
      "loss": 0.18732385635375975,
      "step": 330
    },
    {
      "epoch": 1.5976470588235294,
      "grad_norm": 1.5373793840408325,
      "learning_rate": 4.9094318537852373e-05,
      "loss": 0.2158886194229126,
      "step": 340
    },
    {
      "epoch": 1.644705882352941,
      "grad_norm": 1.0687004327774048,
      "learning_rate": 4.650930798624345e-05,
      "loss": 0.20681512355804443,
      "step": 350
    },
    {
      "epoch": 1.691764705882353,
      "grad_norm": 1.0703026056289673,
      "learning_rate": 4.393364582735292e-05,
      "loss": 0.20864644050598144,
      "step": 360
    },
    {
      "epoch": 1.7388235294117647,
      "grad_norm": 1.7704395055770874,
      "learning_rate": 4.137422992019458e-05,
      "loss": 0.20819923877716065,
      "step": 370
    },
    {
      "epoch": 1.7858823529411765,
      "grad_norm": 2.0520336627960205,
      "learning_rate": 3.883791461483295e-05,
      "loss": 0.21104824542999268,
      "step": 380
    },
    {
      "epoch": 1.8329411764705883,
      "grad_norm": 1.0204700231552124,
      "learning_rate": 3.633149239580659e-05,
      "loss": 0.19849425554275513,
      "step": 390
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.3063665628433228,
      "learning_rate": 3.386167569123274e-05,
      "loss": 0.22384860515594482,
      "step": 400
    },
    {
      "epoch": 1.9270588235294117,
      "grad_norm": 0.9888913631439209,
      "learning_rate": 3.143507889631032e-05,
      "loss": 0.20595297813415528,
      "step": 410
    },
    {
      "epoch": 1.9741176470588235,
      "grad_norm": 1.4625054597854614,
      "learning_rate": 2.9058200659364333e-05,
      "loss": 0.17498573064804077,
      "step": 420
    },
    {
      "epoch": 2.018823529411765,
      "grad_norm": 1.0255882740020752,
      "learning_rate": 2.6737406477870702e-05,
      "loss": 0.15895811319351197,
      "step": 430
    },
    {
      "epoch": 2.0658823529411765,
      "grad_norm": 1.210524320602417,
      "learning_rate": 2.4478911651071455e-05,
      "loss": 0.1364482283592224,
      "step": 440
    },
    {
      "epoch": 2.112941176470588,
      "grad_norm": 1.2359814643859863,
      "learning_rate": 2.2288764634834437e-05,
      "loss": 0.12727158069610595,
      "step": 450
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.444667100906372,
      "learning_rate": 2.0172830843334872e-05,
      "loss": 0.10911383628845214,
      "step": 460
    },
    {
      "epoch": 2.2070588235294117,
      "grad_norm": 0.785530686378479,
      "learning_rate": 1.813677694093935e-05,
      "loss": 0.11209304332733154,
      "step": 470
    },
    {
      "epoch": 2.2541176470588233,
      "grad_norm": 1.415421485900879,
      "learning_rate": 1.618605566636002e-05,
      "loss": 0.09900922775268554,
      "step": 480
    },
    {
      "epoch": 2.3011764705882354,
      "grad_norm": 1.9891433715820312,
      "learning_rate": 1.4325891229721088e-05,
      "loss": 0.12345975637435913,
      "step": 490
    },
    {
      "epoch": 2.348235294117647,
      "grad_norm": 1.630292296409607,
      "learning_rate": 1.2561265321646137e-05,
      "loss": 0.08396114706993103,
      "step": 500
    },
    {
      "epoch": 2.395294117647059,
      "grad_norm": 0.9851526618003845,
      "learning_rate": 1.0896903771834427e-05,
      "loss": 0.11290334463119507,
      "step": 510
    },
    {
      "epoch": 2.4423529411764706,
      "grad_norm": 0.9026244282722473,
      "learning_rate": 9.337263892856623e-06,
      "loss": 0.11543697118759155,
      "step": 520
    },
    {
      "epoch": 2.489411764705882,
      "grad_norm": 0.8032684922218323,
      "learning_rate": 7.886522543063585e-06,
      "loss": 0.11253323554992675,
      "step": 530
    },
    {
      "epoch": 2.5364705882352943,
      "grad_norm": 1.0844193696975708,
      "learning_rate": 6.548564940577467e-06,
      "loss": 0.11062425374984741,
      "step": 540
    },
    {
      "epoch": 2.583529411764706,
      "grad_norm": 1.5046005249023438,
      "learning_rate": 5.32697425832197e-06,
      "loss": 0.09771519303321838,
      "step": 550
    },
    {
      "epoch": 2.630588235294118,
      "grad_norm": 1.1353825330734253,
      "learning_rate": 4.225022027957249e-06,
      "loss": 0.12497321367263795,
      "step": 560
    },
    {
      "epoch": 2.6776470588235295,
      "grad_norm": 1.2384777069091797,
      "learning_rate": 3.2456593784187082e-06,
      "loss": 0.11028198003768921,
      "step": 570
    },
    {
      "epoch": 2.724705882352941,
      "grad_norm": 1.2083806991577148,
      "learning_rate": 2.3915091325235896e-06,
      "loss": 0.11328660249710083,
      "step": 580
    },
    {
      "epoch": 2.7717647058823527,
      "grad_norm": 0.9857290983200073,
      "learning_rate": 1.6648587828114126e-06,
      "loss": 0.13790316581726075,
      "step": 590
    },
    {
      "epoch": 2.8188235294117647,
      "grad_norm": 0.6139959692955017,
      "learning_rate": 1.0676543654295157e-06,
      "loss": 0.08880773782730103,
      "step": 600
    },
    {
      "epoch": 2.8658823529411763,
      "grad_norm": 0.8880029916763306,
      "learning_rate": 6.014952484702241e-07,
      "loss": 0.10029007196426391,
      "step": 610
    },
    {
      "epoch": 2.9129411764705884,
      "grad_norm": 1.115400791168213,
      "learning_rate": 2.676298487166218e-07,
      "loss": 0.11581064462661743,
      "step": 620
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.8476250171661377,
      "learning_rate": 6.695228826819611e-08,
      "loss": 0.11517504453659058,
      "step": 630
    },
    {
      "epoch": 3.0,
      "step": 639,
      "total_flos": 1.9537285221715968e+17,
      "train_loss": 0.2671622457638593,
      "train_runtime": 8374.7877,
      "train_samples_per_second": 0.609,
      "train_steps_per_second": 0.076
    }
  ],
  "logging_steps": 10,
  "max_steps": 639,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9537285221715968e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}